初始化项目,由ModelHub XC社区提供模型
Model: W-61/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725 Source: Original Platform
This commit is contained in:
3
margin_logs/step_0000350.npy
Normal file
3
margin_logs/step_0000350.npy
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:47cacd89d286c2a9bc2f70338f6b19cb3f46b38fe7c4de54b556b0f6b837c44e
|
||||
size 640
|
||||
Reference in New Issue
Block a user